The Agent Skills Directory

[SAFE]: The skill consists entirely of markdown-based documentation and instructional frameworks. There are no scripts (Python, Node.js, Shell), binaries, or automation instructions that could be executed by an agent.
[EXTERNAL_DOWNLOADS]: The documentation references several legitimate third-party marketing and analytics platforms (e.g., Huitun Data, Chanmama, Brandwatch, and Mention.com). These references are informational recommendations for the user's workflow and do not involve any automated downloads or remote code execution by the agent.
[INDIRECT_PROMPT_INJECTION]: While the skill describes a process that involves ingesting untrusted data (user comments and brand mentions), it does not provide code to perform this ingestion, nor does it define prompt structures that would be vulnerable. It functions as a strategic guide rather than a functional tool.

sentiment-monitoring